Merge branch 'k.o/for-4.3-v1' into k.o/for-4.4

Pick up the late fixes from the 4.3 cycle so we have them in our
next branch.

7 files changed, 70 insertions, 28 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index ca2873698d75..edc5b8565d6d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -80,7 +80,7 @@ enum {
 	IPOIB_NUM_WC		  = 4,
 
 	IPOIB_MAX_PATH_REC_QUEUE  = 3,
-	IPOIB_MAX_MCAST_QUEUE	  = 3,
+	IPOIB_MAX_MCAST_QUEUE	  = 64,
 
 	IPOIB_FLAG_OPER_UP	  = 0,
 	IPOIB_FLAG_INITIALIZED	  = 1,
@@ -495,6 +495,7 @@ void ipoib_dev_cleanup(struct net_device *dev);
 void ipoib_mcast_join_task(struct work_struct *work);
 void ipoib_mcast_carrier_on_task(struct work_struct *work);
 void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb);
+void ipoib_mcast_free(struct ipoib_mcast *mc);
 
 void ipoib_mcast_restart_task(struct work_struct *work);
 int ipoib_mcast_start_thread(struct net_device *dev);
@@ -548,6 +549,8 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter,
 
 int ipoib_mcast_attach(struct net_device *dev, u16 mlid,
 		       union ib_gid *mgid, int set_qkey);
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast);
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid);
 
 int ipoib_init_qp(struct net_device *dev);
 int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 36536ce5a3e2..babba05d7a0e 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1149,6 +1149,9 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 	unsigned long dt;
 	unsigned long flags;
 	int i;
+	LIST_HEAD(remove_list);
+	struct ipoib_mcast *mcast, *tmcast;
+	struct net_device *dev = priv->dev;
 
 	if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
 		return;
@@ -1176,6 +1179,19 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 							  lockdep_is_held(&priv->lock))) != NULL) {
 			/* was the neigh idle for two GC periods */
 			if (time_after(neigh_obsolete, neigh->alive)) {
+				u8 *mgid = neigh->daddr + 4;
+
+				/* Is this multicast ? */
+				if (*mgid == 0xff) {
+					mcast = __ipoib_mcast_find(dev, mgid);
+
+					if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
+						list_del(&mcast->list);
+						rb_erase(&mcast->rb_node, &priv->multicast_tree);
+						list_add_tail(&mcast->list, &remove_list);
+					}
+				}
+
 				rcu_assign_pointer(*np,
 						   rcu_dereference_protected(neigh->hnext,
 									     lockdep_is_held(&priv->lock)));
@@ -1191,6 +1207,10 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 
 out_unlock:
 	spin_unlock_irqrestore(&priv->lock, flags);
+	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
+		ipoib_mcast_leave(dev, mcast);
+		ipoib_mcast_free(mcast);
+	}
 }
 
 static void ipoib_reap_neigh(struct work_struct *work)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 09a1748f9d13..d750a86042f3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -106,7 +106,7 @@ static void __ipoib_mcast_schedule_join_thread(struct ipoib_dev_priv *priv,
 		queue_delayed_work(priv->wq, &priv->mcast_task, 0);
 }
 
-static void ipoib_mcast_free(struct ipoib_mcast *mcast)
+void ipoib_mcast_free(struct ipoib_mcast *mcast)
 {
 	struct net_device *dev = mcast->dev;
 	int tx_dropped = 0;
@@ -153,7 +153,7 @@ static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev,
 	return mcast;
 }
 
-static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct rb_node *n = priv->multicast_tree.rb_node;
@@ -508,17 +508,19 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;
 
 		/*
-		 * Historically Linux IPoIB has never properly supported SEND
-		 * ONLY join. It emulated it by not providing all the required
-		 * attributes, which is enough to prevent group creation and
-		 * detect if there are full members or not. A major problem
-		 * with supporting SEND ONLY is detecting when the group is
-		 * auto-destroyed as IPoIB will cache the MLID..
+		 * Send-only IB Multicast joins do not work at the core
+		 * IB layer yet, so we can't use them here.  However,
+		 * we are emulating an Ethernet multicast send, which
+		 * does not require a multicast subscription and will
+		 * still send properly.  The most appropriate thing to
+		 * do is to create the group if it doesn't exist as that
+		 * most closely emulates the behavior, from a user space
+		 * application perspecitive, of Ethernet multicast
+		 * operation.  For now, we do a full join, maybe later
+		 * when the core IB layers support send only joins we
+		 * will use them.
 		 */
-#if 1
-		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-			comp_mask &= ~IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;
-#else
+#if 0
 		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
 			rec.join_state = 4;
 #endif
@@ -675,7 +677,7 @@ int ipoib_mcast_stop_thread(struct net_device *dev)
 	return 0;
 }
 
-static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret = 0;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 1ace5d83a4d7..f58ff96b6cbb 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -97,6 +97,11 @@ unsigned int iser_max_sectors = ISER_DEF_MAX_SECTORS;
 module_param_named(max_sectors, iser_max_sectors, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(max_sectors, "Max number of sectors in a single scsi command (default:1024");
 
+bool iser_always_reg = true;
+module_param_named(always_register, iser_always_reg, bool, S_IRUGO);
+MODULE_PARM_DESC(always_register,
+		 "Always register memory, even for continuous memory regions (default:true)");
+
 bool iser_pi_enable = false;
 module_param_named(pi_enable, iser_pi_enable, bool, S_IRUGO);
 MODULE_PARM_DESC(pi_enable, "Enable T10-PI offload support (default:disabled)");
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 86f6583485ef..a5edd6ede692 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -611,6 +611,7 @@ extern int iser_debug_level;
 extern bool iser_pi_enable;
 extern int iser_pi_guard;
 extern unsigned int iser_max_sectors;
+extern bool iser_always_reg;
 
 int iser_assign_reg_ops(struct iser_device *device);
 
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 2493cc748db8..4c46d67d37a1 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -803,11 +803,12 @@ static int
 iser_reg_prot_sg(struct iscsi_iser_task *task,
 		 struct iser_data_buf *mem,
 		 struct iser_fr_desc *desc,
+		 bool use_dma_key,
 		 struct iser_mem_reg *reg)
 {
 	struct iser_device *device = task->iser_conn->ib_conn.device;
 
-	if (mem->dma_nents == 1)
+	if (use_dma_key)
 		return iser_reg_dma(device, mem, reg);
 
 	return device->reg_ops->reg_mem(task, mem, &desc->pi_ctx->rsc, reg);
@@ -817,11 +818,12 @@ static int
 iser_reg_data_sg(struct iscsi_iser_task *task,
 		 struct iser_data_buf *mem,
 		 struct iser_fr_desc *desc,
+		 bool use_dma_key,
 		 struct iser_mem_reg *reg)
 {
 	struct iser_device *device = task->iser_conn->ib_conn.device;
 
-	if (mem->dma_nents == 1)
+	if (use_dma_key)
 		return iser_reg_dma(device, mem, reg);
 
 	return device->reg_ops->reg_mem(task, mem, &desc->rsc, reg);
@@ -836,14 +838,17 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 	struct iser_mem_reg *reg = &task->rdma_reg[dir];
 	struct iser_mem_reg *data_reg;
 	struct iser_fr_desc *desc = NULL;
+	bool use_dma_key;
 	int err;
 
 	err = iser_handle_unaligned_buf(task, mem, dir);
 	if (unlikely(err))
 		return err;
 
-	if (mem->dma_nents != 1 ||
-	    scsi_get_prot_op(task->sc) != SCSI_PROT_NORMAL) {
+	use_dma_key = (mem->dma_nents == 1 && !iser_always_reg &&
+		       scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL);
+
+	if (!use_dma_key) {
 		desc = device->reg_ops->reg_desc_get(ib_conn);
 		reg->mem_h = desc;
 	}
@@ -853,7 +858,7 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 	else
 		data_reg = &task->desc.data_reg;
 
-	err = iser_reg_data_sg(task, mem, desc, data_reg);
+	err = iser_reg_data_sg(task, mem, desc, use_dma_key, data_reg);
 	if (unlikely(err))
 		goto err_reg;
 
@@ -866,7 +871,8 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 			if (unlikely(err))
 				goto err_reg;
 
-			err = iser_reg_prot_sg(task, mem, desc, prot_reg);
+			err = iser_reg_prot_sg(task, mem, desc,
+					       use_dma_key, prot_reg);
 			if (unlikely(err))
 				goto err_reg;
 		}
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index ae70cc1463ac..85132d867bc8 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -133,11 +133,15 @@ static int iser_create_device_ib_res(struct iser_device *device)
 			     (unsigned long)comp);
 	}
 
-	device->mr = ib_get_dma_mr(device->pd, IB_ACCESS_LOCAL_WRITE |
-				   IB_ACCESS_REMOTE_WRITE |
-				   IB_ACCESS_REMOTE_READ);
-	if (IS_ERR(device->mr))
-		goto dma_mr_err;
+	if (!iser_always_reg) {
+		int access = IB_ACCESS_LOCAL_WRITE |
+			     IB_ACCESS_REMOTE_WRITE |
+			     IB_ACCESS_REMOTE_READ;
+
+		device->mr = ib_get_dma_mr(device->pd, access);
+		if (IS_ERR(device->mr))
+			goto dma_mr_err;
+	}
 
 	INIT_IB_EVENT_HANDLER(&device->event_handler, device->ib_device,
 				iser_event_handler);
@@ -147,7 +151,8 @@ static int iser_create_device_ib_res(struct iser_device *device)
 	return 0;
 
 handler_err:
-	ib_dereg_mr(device->mr);
+	if (device->mr)
+		ib_dereg_mr(device->mr);
 dma_mr_err:
 	for (i = 0; i < device->comps_used; i++)
 		tasklet_kill(&device->comps[i].tasklet);
@@ -173,7 +178,6 @@ comps_err:
 static void iser_free_device_ib_res(struct iser_device *device)
 {
 	int i;
-	BUG_ON(device->mr == NULL);
 
 	for (i = 0; i < device->comps_used; i++) {
 		struct iser_comp *comp = &device->comps[i];
@@ -184,7 +188,8 @@ static void iser_free_device_ib_res(struct iser_device *device)
 	}
 
 	(void)ib_unregister_event_handler(&device->event_handler);
-	(void)ib_dereg_mr(device->mr);
+	if (device->mr)
+		(void)ib_dereg_mr(device->mr);
 	ib_dealloc_pd(device->pd);
 
 	kfree(device->comps);